mlsanityData to 7 Oct 2026

Towards PAC Multi-Object Detection and Tracking

arXiv 2204.07482 ↗First posted 15 Apr 2022cs.CV cs.LGcited by 8

Not on the map. Why?

Abstract (arXiv)

Accurately detecting and tracking multi-objects is important for safety-critical applications such as autonomous navigation. However, it remains challenging to provide guarantees on the performance of state-of-the-art techniques based on deep learning. We consider a strategy known as conformal prediction, which predicts sets of labels instead of a single label; in the classification and regression settings, these algorithms can guarantee that the true label lies within the prediction set with high probability. Building on these ideas, we propose multi-object detection and tracking algorithms that come with probably approximately correct (PAC) guarantees. They do so by constructing both a prediction set around each object detection as well as around the set of edge transitions; given an object, the detection prediction set contains its true bounding box with high probability, and the edge prediction set contains its true transition across frames with high probability. We empirically demonstrate that our method can detect and track objects with PAC guarantees on the COCO and MOT-17 datasets.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 31 of its 46 references that are in the map. First posted on arXiv 15 Apr 2022.

Builds on

31 of 46 references.

References · 31

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  3. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  4. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  5. 2017Mask R-CNNcited by 7,259
  6. 2017On Calibration of Modern Neural Networkscited by 4,860
  7. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,829
  8. 2015SSD: Single Shot MultiBox Detectorcited by 3,125
  9. 2015Fast R-CNNcited by 2,930
  10. 2020YOLOv4: Optimal Speed and Accuracy of Object Detectioncited by 1,624
  11. 2016YOLO9000: Better, Faster, Strongercited by 1,429
  12. 2017Cascade R-CNN: Delving into High Quality Object Detectioncited by 1,275
19 more
  1. 2016Simple Online and Realtime Trackingcited by 862
  2. 2017Focal Loss for Dense Object Detectioncited by 749
  3. 2021A Survey of Uncertainty in Deep Neural Networkscited by 675
  4. 2016MOT16: A Benchmark for Multi-Object Trackingcited by 531
  5. 2019Hybrid Task Cascade for Instance Segmentationcited by 479
  6. 2018Accurate Uncertainties for Deep Learning Using Calibrated Regressioncited by 417
  7. 2019Tracking without bells and whistlescited by 382
  8. 2020DetectoRS: Detecting Objects with Recursive Feature Pyramid and Switchable Atrous Convolutioncited by 222
  9. 2014Multiple Object Tracking: A Literature Reviewcited by 165
  10. 2021Track to Detect and Segment: An Online Multi-Object Trackercited by 156
  11. 2019Deep Learning in Video Multi-Object Tracking: A Surveycited by 107
  12. 2018Real-time Multiple People Tracking with Deeply Learned Candidate Selection and Person Re-Identificationcited by 96
  13. 2018Joint Monocular 3D Vehicle Detection and Trackingcited by 77
  14. 2021SiamMOT: Siamese Multi-Object Trackingcited by 62
  15. 2019PAC Confidence Sets for Deep Neural Networks via Calibrated Predictioncited by 59
  16. 2021Estimating and Evaluating Regression Predictive Uncertainty in Deep Object Detectorscited by 37
  17. 2019Calibrated Model-Based Deep Reinforcement Learningcited by 31
  18. 2016Multi-Person Tracking by Multicut and Deep Matchingcited by 23
  19. 2020PAC Confidence Predictions for Deep Neural Network Classifierscited by 21

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 3; 2024: 1; 2025: 3; 2026: 1.

8 papers.

  1. 2023Object Pose Estimation with Statistical Guarantees: Conformal Keypoint Detection and Geometric Uncertainty Propagationcited by 33
  2. 2024Adaptive Bounding Box Uncertainties via Two-Step Conformal Predictioncited by 23
  3. 2023Confident Object Detection via Conformal Prediction and Conformal Risk Control: an Application to Railway Signalingcited by 22
  4. 2025Conformal Prediction for Image Segmentation Using Morphological Prediction Setscited by 13
  5. 2023Conformal Prediction for Trustworthy Detection of Railway Signalscited by 7
  6. 2025Conformal Prediction and MLLM aided Uncertainty Quantification in Scene Graph Generationcited by 7
  7. 2025Conformal Object Detection by Sequential Risk Controlcited by 3
  8. 2026Conformal Prediction Sets for Instance Segmentationcited by 1